youtube_abschrift_korrigieren/tests/test_extract_text.py

"""Tests for extract_text.py; yt-dlp is always replaced by fakes (no network)."""
import json
import sys

import pytest

import extract_text
import yt_untertitel as yt

URL = "https://www.youtube.com/watch?v=abc123"

VTT = (
    "WEBVTT\n\n"
    "00:00:01.000 --> 00:00:02.000\n \nGuten<00:00:01.500><c> Abend.</c>\n\n"
    "00:00:02.000 --> 00:00:03.000\nGuten Abend.\nSchön, dass Sie da sind.\n"
)

GERMAN_VIDEO = {
    "id": "abc123",
    "title": "Eine Rede",
    "channel": "Kanal",
    "upload_date": "20260328",
    "subtitles": {"en": []},
    "automatic_captions": {"de-orig": [], "de": [], "en": []},
}


pytestmark = pytest.mark.usefixtures("yt_dlp_installed")


def run_main(monkeypatch, *args):
    monkeypatch.setattr(sys, "argv", ["extract_text.py", *map(str, args)])
    extract_text.main()


def test_default_language_is_original_audio(fake_yt_dlp, tmp_path, monkeypatch, capsys):
    run = fake_yt_dlp(GERMAN_VIDEO, vtt=VTT)
    monkeypatch.setattr(yt.subprocess, "run", run)
    monkeypatch.chdir(tmp_path)
    run_main(monkeypatch, "-u", URL)

    work = tmp_path / "abschriften" / "Kanal_Eine_Rede_2026-03-28"
    text = (work / "Kanal_Eine_Rede_2026-03-28.txt").read_text(encoding="utf-8")
    assert text == "Guten Abend.\nSchön, dass Sie da sind.\n"
    assert "de-orig" in run.calls[1]
    assert "--write-auto-subs" in run.calls[1]
    out = capsys.readouterr().out
    assert "Kanal_Eine_Rede_2026-03-28.txt (2 Zeilen, 7 Wörter)" in out
    # Only the text file and where it comes from remain, no VTT
    assert sorted(p.name for p in work.iterdir()) == [
        "Kanal_Eine_Rede_2026-03-28.quelle.json", "Kanal_Eine_Rede_2026-03-28.txt",
    ]
    source = json.loads((work / "Kanal_Eine_Rede_2026-03-28.quelle.json").read_text())
    assert source["kanal"] == "Kanal" and source["url"].endswith("v=abc123")


def test_default_language_ignores_dubbed_tracks(fake_yt_dlp, tmp_path, monkeypatch):
    info = {
        "id": "dub", "language": "en-US", "subtitles": {"en-US": []},
        "automatic_captions": {"ar-orig": [], "en-orig": []},
    }
    run = fake_yt_dlp(info, vtt=VTT)
    monkeypatch.setattr(yt.subprocess, "run", run)
    run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt")
    download = run.calls[1]
    assert download[download.index("--sub-langs") + 1] == "en-US"
    assert "--write-subs" in download


def test_fliesstext(fake_yt_dlp, tmp_path, monkeypatch, capsys):
    long_vtt = "WEBVTT\n\n" + "".join(
        f"00:00:{i:02d}.000 --> 00:00:{i + 1:02d}.000\nSatz Nummer {i} zum EU-Gipfel.\n\n"
        for i in range(20)
    )
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt=long_vtt))
    target = tmp_path / "rede.txt"
    run_main(monkeypatch, "-u", URL, "-f", "-o", target)

    lines = target.read_text(encoding="utf-8").splitlines()
    assert 1 < len(lines) < 20
    assert all(len(line) <= extract_text.FLOW_WIDTH for line in lines)
    assert " ".join(lines) == " ".join(f"Satz Nummer {i} zum EU-Gipfel." for i in range(20))
    assert "100 Wörter" in capsys.readouterr().out


def test_explicit_language_prefers_manual(fake_yt_dlp, tmp_path, monkeypatch):
    run = fake_yt_dlp(GERMAN_VIDEO, vtt=VTT)
    monkeypatch.setattr(yt.subprocess, "run", run)
    target = tmp_path / "neu" / "rede.en.txt"
    run_main(monkeypatch, "-u", URL, "-l", "en", "-o", target)

    assert target.is_file()
    assert "--write-subs" in run.calls[1]


def test_original_language_from_metadata_without_auto_captions(
    fake_yt_dlp, tmp_path, monkeypatch
):
    info = {"id": "x", "language": "fr", "subtitles": {"fr": []}, "automatic_captions": {}}
    run = fake_yt_dlp(info, vtt=VTT)
    monkeypatch.setattr(yt.subprocess, "run", run)
    run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt")
    assert run.calls[1][run.calls[1].index("--sub-langs") + 1] == "fr"


@pytest.mark.parametrize("info, args, message", [
    # Translation only: no "en-orig", no manual "en"
    (GERMAN_VIDEO, ["-l", "fr"], "Keine Untertitel in „fr“"),
    ({"id": "x", "subtitles": {}, "automatic_captions": {}}, [], "Originalsprache"),
])
def test_no_matching_track(fake_yt_dlp, tmp_path, monkeypatch, info, args, message):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(info, vtt=VTT))
    with pytest.raises(SystemExit, match=message):
        run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt", *args)
    assert not (tmp_path / "out.txt").exists()


def test_empty_subtitles(fake_yt_dlp, tmp_path, monkeypatch):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt="WEBVTT\n"))
    with pytest.raises(SystemExit, match="keinen Text"):
        run_main(monkeypatch, "-u", URL, "-o", tmp_path / "out.txt")


@pytest.mark.parametrize("args, message", [
    ([], "required"),
    (["-u", URL, "-o", "{dir}"], "ist ein Verzeichnis"),
])
def test_cli_errors(tmp_path, monkeypatch, capsys, args, message):
    args = [a.format(dir=tmp_path) for a in args]
    with pytest.raises(SystemExit) as exc:
        run_main(monkeypatch, *args)
    assert exc.value.code == 2
    assert message in capsys.readouterr().err


def test_time_range_default_name(fake_yt_dlp, tmp_path, monkeypatch):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt=VTT))
    monkeypatch.chdir(tmp_path)
    run_main(monkeypatch, "-u", URL, "-z", "0:00:02-0:00:03")

    name = "Kanal_Eine_Rede_2026-03-28_00-00-02_bis_00-00-03.txt"
    work = tmp_path / "abschriften" / "Kanal_Eine_Rede_2026-03-28"
    assert (work / name).read_text(encoding="utf-8") == (
        "[00:00:02 - 00:00:03]\nSchön, dass Sie da sind.\n"
    )


def test_time_range_without_text(fake_yt_dlp, tmp_path, monkeypatch):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt=VTT))
    with pytest.raises(SystemExit, match="im gewählten Zeitraum keinen Text"):
        run_main(monkeypatch, "-u", URL, "-z", "1:00", "-o", tmp_path / "out.txt")


def test_time_range_order_error(monkeypatch, capsys):
    with pytest.raises(SystemExit) as exc:
        run_main(monkeypatch, "-u", URL, "-z", "2:00-1:00")
    assert exc.value.code == 2
    assert "Start muss vor Ende" in capsys.readouterr().err


CUT_VTT = (
    "WEBVTT\n\n00:00:01.000 --> 00:00:02.000\nGuten Abend und\n\n"
    "00:00:02.000 --> 00:00:03.000\nwillkommen. Schön, dass\n\n"
    "00:00:03.000 --> 00:00:04.000\nSie da sind.\n"
)


@pytest.mark.parametrize("exact, text", [
    ([], "[00:00:01 - 00:00:04]\nGuten Abend und\nwillkommen. Schön, dass\nSie da sind.\n"),
    (["--exakt"], "[00:00:02 - 00:00:03]\nwillkommen. Schön, dass\n"),
])
def test_time_range_sentence_bounds(fake_yt_dlp, tmp_path, monkeypatch, exact, text):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt=CUT_VTT))
    target = tmp_path / "out.txt"
    run_main(monkeypatch, "-u", URL, "-z", "0:00:02-0:00:03", "-o", target, *exact)
    assert target.read_text(encoding="utf-8") == text


MULTI_VTT = (
    "WEBVTT\n\n00:00:01.000 --> 00:00:02.000\nErster Satz der Rede.\n\n"
    "00:01:00.000 --> 00:01:01.000\nZweiter Satz.\n\n"
    "00:02:00.000 --> 00:02:01.000\nDritter Satz, der etwas länger ist.\n"
)


def test_several_ranges_flow_text_keeps_headers(fake_yt_dlp, tmp_path, monkeypatch, capsys):
    monkeypatch.setattr(yt.subprocess, "run", fake_yt_dlp(GERMAN_VIDEO, vtt=MULTI_VTT))
    monkeypatch.setattr(extract_text, "FLOW_WIDTH", 20)
    monkeypatch.chdir(tmp_path)
    run_main(monkeypatch, "-u", URL, "-z", "0:00:00-0:00:30 0:02", "-f")

    name = "Kanal_Eine_Rede_2026-03-28_bis_00-00-30+ab_00-02-00.txt"
    work = tmp_path / "abschriften" / "Kanal_Eine_Rede_2026-03-28"
    assert (work / name).read_text(encoding="utf-8") == (
        "[00:00:01 - 00:00:02]\nErster Satz der\nRede.\n\n"
        "[00:02:00 - 00:02:01]\nDritter Satz, der\netwas länger ist.\n"
    )
    assert "(7 Zeilen, 10 Wörter)" in capsys.readouterr().out